NANI-Nithin/VoxCPM2-GGUF
Same weights, converted vs openbmb/VoxCPM2. Same weights stored in another dtype (BF16 → F16/I32), plus 444 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/71, MLP 0/128, Attention 0/160, other 0/10
Same weights, converted vs openbmb/VoxCPM2. Same weights stored in another dtype (BF16 → F16/I32), plus 444 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/71, MLP 0/128, Attention 0/160, other 0/10